Slug Mobile: Test-Bench for RL Testing

TL;DR

Slug Mobile introduces a one-tenth scale autonomous vehicle designed to bridge the sim-to-real gap in RL for autonomous driving. By combining updated hardware (including a Dynamic Vision Sensor for SNNs) with a ROS-free software stack and a CARLA-based OpenAI Gym environment, the work provides a practical platform to train RL policies in simulation and transfer them to a real vehicle. Key contributions include a custom hardware integration for simplified RL troubleshooting, and the use of CARLA-Gym for scalable policy development with a plan to build multi-sensor imitation-learning datasets leveraging neuromorphic hardware. This platform has the potential to accelerate robust sim-to-real transfer and enable efficient testing across vehicle variants.

Abstract

Sim-to real gap in Reinforcement Learning is when a model trained in a simulator does not translate to the real world. This is a problem for Autonomous Vehicles (AVs) as vehicle dynamics can vary from simulation to reality, and also from vehicle to vehicle. Slug Mobile is a one tenth scale autonomous vehicle created to help address the sim-to-real gap for AVs by acting as a test-bench to develop models that can easily scale from one vehicle to another. In addition to traditional sensors found in other one tenth scale AVs, we have also included a Dynamic Vision Sensor so we can train Spiking Neural Networks running on neuromorphic hardware.

Figures (2)

• Figure 1: Slug Mobile: One Tenth Autonomous Vehicle for sim-to-real testing
• Figure 2: Example visualization of CARLA environment